Development and validation of risk prediction and neural network models for dilated cardiomyopathy based on WGCNA

作者全名："Yu, Wei; Li, Lingjiao; Tan, Xingling; Liu, Xiaozhu; Yin, Chengliang; Cao, Junyi"

作者地址："[Yu, Wei; Li, Lingjiao; Tan, Xingling; Liu, Xiaozhu] Chongqing Med Univ, Chongqing, Peoples R China; [Yin, Chengliang] Macau Univ Sci & Technol, Fac Med, Taipa, Macau, Peoples R China; [Cao, Junyi] First Peoples Hosp Zigong City, Dept Med Qual Control, Zigong, Peoples R China"

通信作者："Yin, CL (通讯作者)，Macau Univ Sci & Technol, Fac Med, Taipa, Macau, Peoples R China.; Cao, JY (通讯作者)，First Peoples Hosp Zigong City, Dept Med Qual Control, Zigong, Peoples R China."

来源：FRONTIERS IN MEDICINE

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001087492400001

JCR分区：Q1

影响因子：3.1

年份：2023

卷号：10

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：dilated cardiomyopathy; weighted gene co-expression network analysis; risk prediction model; neural network model; bioinformatics

摘要："BackgroundDilated cardiomyopathy (DCM) is a progressive heart condition characterized by ventricular dilatation and impaired myocardial contractility with a high mortality rate. The molecular characterization of DCM has not been determined yet. Therefore, it is crucial to discover potential biomarkers and therapeutic options for DCM.MethodsThe hub genes for the DCM were screened using Weighted Gene Co-expression Network Analysis (WGCNA) and three different algorithms in Cytoscape. These genes were then validated in a mouse model of doxorubicin (DOX)-induced DCM. Based on the validated hub genes, a prediction model and a neural network model were constructed and validated in a separate dataset. Finally, we assessed the diagnostic efficiency of hub genes and their relationship with immune cells.ResultsA total of eight hub genes were identified. Using RT-qPCR, we validated that the expression levels of five key genes (ASPN, MFAP4, PODN, HTRA1, and FAP) were considerably higher in DCM mice compared to normal mice, and this was consistent with the microarray results. Additionally, the risk prediction and neural network models constructed from these genes showed good accuracy and sensitivity in both the combined and validation datasets. These genes also demonstrated better diagnostic power, with AUC greater than 0.7 in both the combined and validation datasets. Immune cell infiltration analysis revealed differences in the abundance of most immune cells between DCM and normal samples.ConclusionThe current findings indicate an underlying association between DCM and these key genes, which could serve as potential biomarkers for diagnosing and treating DCM."

基金机构："We would like to express our gratitude to the providers of the datasets GSE57338, GSE120895, and GSE116250 for sharing the data online. We thank Tao Ling for his help in model construction and manuscript revision. [GSE120895, GSE116250]"

基金资助正文："We would like to express our gratitude to the providers of the datasets GSE57338, GSE120895, and GSE116250 for sharing the data online. We thank Tao Ling for his help in model construction and manuscript revision."